🔄Update: [Lab-2] 模型训练与测试

Lab-2/src/data_transform.py

@@ -18,7 +18,7 @@ def get_transform():
     ])
 
 
-def load_mnist(data_size=100, batch_size=16, seed=42, root='../data'):
+def load_mnist(data_size=100, batch_size=16, seed=42, root='../data', train=True):
     """
     加载 MNIST 数据集。
 
@@ -27,32 +27,33 @@ def load_mnist(data_size=100, batch_size=16, seed=42, root='../data'):
     - batch_size (int): 每批次处理的数据数量。
     - seed (int): 随机种子，用于保证数据切割的可重复性。
     - root (str): 数据集保存的路径。
+    - train (bool): 是否加载训练集。
 
     Returns:
-    - train_loader (DataLoader): 训练数据集加载器。
+    - DataLoader: 数据加载器。
     """
     transform = get_transform()
 
-    train_dataset = torchvision.datasets.MNIST(
+    dataset = torchvision.datasets.MNIST(
         root=root,
-        train=True,
+        train=train,
         download=True,
         transform=transform
     )
 
-    data_train, _ = random_split(
-        dataset=train_dataset,
-        lengths=[data_size, len(train_dataset) - data_size],
+    data_subset, _ = random_split(
+        dataset=dataset,
+        lengths=[data_size, len(dataset) - data_size],
         generator=torch.Generator().manual_seed(seed)
     )
 
-    train_loader = DataLoader(
-        dataset=data_train,
+    data_loader = DataLoader(
+        dataset=data_subset,
         batch_size=batch_size,
         shuffle=True
     )
 
-    return train_loader
+    return data_loader
 
 
 def load_and_preview_mnist(data_size=100, batch_size=16, seed=42, root='../data'):
@@ -65,14 +66,14 @@ def load_and_preview_mnist(data_size=100, batch_size=16, seed=42, root='../data'
     - seed (int): 随机种子，用于保证数据切割的可重复性。
     - root (str): 数据集保存的路径。
     """
-    train_loader = load_mnist(data_size=data_size, batch_size=batch_size, seed=seed, root=root)
+    train_loader = load_mnist(data_size=data_size, batch_size=batch_size, seed=seed, root=root, train=True)
 
     images, labels = next(iter(train_loader))
 
     img_grid = torchvision.utils.make_grid(images, nrow=batch_size // 4)
     img = img_grid.numpy().transpose(1, 2, 0)
-    mean = [0.5, 0.5, 0.5]
-    std = [0.5, 0.5, 0.5]
+    mean = [0.5]
+    std = [0.5]
     img = img * std + mean
 
     print([labels[i] for i in range(batch_size)])
@@ -85,4 +86,4 @@ if __name__ == '__main__':
     load_and_preview_mnist()
 
     # Or use custom parameters:
-    # load_and_preview_mnist(data_size=200, batch_size=8, seed=123, root='../data')
+    # load_and_preview_mnist(data_size=200, batch_size=8, seed=123, root='./data')

Lab-2/src/model_training.py

@@ -0,0 +1,116 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import DataLoader
+from data_transform import load_mnist, load_and_preview_mnist
+import matplotlib.pyplot as plt
+import torchvision.utils as vutils
+
+
+# 定义卷积神经网络模型
+class Model(nn.Module):
+    def __init__(self):
+        super(Model, self).__init__()
+        self.conv1 = nn.Sequential(
+            nn.Conv2d(1, 64, kernel_size=3, stride=2, padding=1),
+            nn.ReLU(),
+            nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1),
+            nn.ReLU(),
+            # nn.MaxPool2d(stride=2, kernel_size=2)
+        )
+
+        self.dense = nn.Sequential(
+            nn.Linear(7 * 7 * 128, 512),
+            nn.ReLU(),
+            nn.Dropout(p=0.8),
+            nn.Linear(512, 10)
+        )
+
+    def forward(self, x):
+        x = self.conv1(x)  # 卷积处理
+        x = x.view(-1, 7 * 7 * 128)  # 对参数实行扁平化处理
+        x = self.dense(x)
+        return x
+
+
+# 加载和预览数据集
+def main():
+    # 参数设置
+    data_size = 1000
+    batch_size = 4
+    seed = 42
+    root = '../data'
+    epochs_n = 5
+    learning_rate = 0.001
+
+    # 加载数据加载器
+    train_loader = load_mnist(data_size=data_size, batch_size=batch_size, seed=seed, root=root, train=True)
+    test_loader = load_mnist(data_size=data_size, batch_size=batch_size, seed=seed, root=root, train=False)
+
+    # 预览数据集（可选）
+    load_and_preview_mnist(data_size=data_size, batch_size=batch_size, seed=seed, root=root)
+
+    # 初始化模型
+    model = Model()
+    cost = nn.CrossEntropyLoss()
+    optimizer = optim.Adam(model.parameters(), lr=learning_rate)
+
+    # 训练模型
+    for epoch in range(epochs_n):
+        model.train()
+        running_loss = 0.0
+        running_correct = 0
+        print(f"Epoch {epoch + 1}/{epochs_n}")
+        print("-" * 10)
+
+        for data in train_loader:
+            images, labels = data
+            optimizer.zero_grad()
+            outputs = model(images)
+            _, preds = torch.max(outputs.data, 1)
+            loss = cost(outputs, labels)
+            loss.backward()
+            optimizer.step()
+            running_loss += loss.item()
+            running_correct += (preds == labels).sum().item()
+
+        epoch_loss = running_loss / len(train_loader.dataset)
+        epoch_acc = 100 * running_correct / len(train_loader.dataset)
+
+        print(f"Loss: {epoch_loss:.4f}, Train Accuracy: {epoch_acc:.4f}%")
+
+        # 测试模型
+        model.eval()
+        testing_correct = 0
+        with torch.no_grad():
+            for data in test_loader:
+                images, labels = data
+                outputs = model(images)
+                _, preds = torch.max(outputs.data, 1)
+                testing_correct += (preds == labels).sum().item()
+
+            test_acc = 100 * testing_correct / len(test_loader.dataset)
+            print(f"Test Accuracy: {test_acc:.4f}%")
+
+    # 测试数据可视化
+    X_test, y_test = next(iter(test_loader))
+    with torch.no_grad():
+        pred = model(X_test)
+        _, predicted_labels = torch.max(pred, 1)
+
+    print("Predicted Labels:", [i.item() for i in predicted_labels])
+    print("True Labels:", [i.item() for i in y_test])
+
+    # 显示图像
+    img_grid = vutils.make_grid(X_test, nrow=batch_size // 4)
+    img = img_grid.numpy().transpose(1, 2, 0)
+    mean = [0.5]
+    std = [0.5]
+    img = img * std + mean
+    plt.imshow(img, cmap='gray')
+    plt.axis('off')
+    plt.show()
+
+
+if __name__ == '__main__':
+    main()